Title
A Research Retrospective on AMD's Exascale Computing JourneyConference
Published in the Proceedings of the 50th Annual International Symposium on Computer Architecture (ISCA 2023), June, 2023 (industry session acceptance rate: 5/11 ≈ 45%)Authors
Gabriel H. Loh, Michael J. Schulte, Mike Ignatowski, Vignesh Adhinarayanan, Shaizeen Aga, Derrick Aguren, Varun Agrawal, Ashwin M. Aji, John Alsop, Paul Bauman, Bradford M. Beckmann, Majed Valad Beigi, Sergey Blagodurov, Travis Boraten, Michael Boyer, William Brantley, Noel Chalmers, Shaoming Chen, Kevin Cheng, Michael L. Chu, David Cownie, Nicholas Curtis, Joris Del Pino, Nam Duong, Alexandru Dutu, Yasuko Eckert, Christopher Erb, Chip Freitag, Joseph L. Greathouse, Sudhanva Gurumurthi, Anthony Gutierrez, Khaled Hamidouche, Sachin Hossamani, Wei Huang, Mahzabeen Islam, Nuwan Jayasena, John Kalamatianos, Onur Kayiran, Jagadish Kotra, Alan Lee, Daniel Lowell, Niti Madan, Abhinandan Majumdar, Nicholas Malaya, Srilatha Manne, Susumu Mashimo, Damon McDougall, Elliott Mednick, Michael Mishkin, Mark Nutter, Indrani Paul, Matthew Poremba, Brandon Potter, Kishore Punniyamurthy, Sooraj Puthoor, Steven E. Raasch, Karthik Rao, Greg Rodgers, Marko Scrbak, Mohammad Seyedzadeh, John Slice, Vilas Sridharan, Rene van Oostrum, Eric van Tassell, Abhinav Vishnu, Samuel Wasmundt, Mark Wilkening, Noah Wolfe, Mark Wyse, Adithya Yalavarti, Dmitri YudanovAbstract
The pace of advancement of the top-end supercomputers historically followed an exponential curve similar to (and driven in part by) Moore's Law. Shortly after hitting the petaflop mark, the community started looking ahead to the next milestone: Exascale. However, many obstacles were already looming on the horizon, such as the slowing of Moore's Law, and others like the end of Dennard Scaling had already arrived. Anticipating significant challenges for the overall high-performance computing (HPC) community to achieve the next 1000x improvement, the U.S. Department of Energy (DOE) launched the Exascale Computing Program to enable and accelerate fundamental research across the many technologies needed to achieve exascale computing.
AMD had the opportunity to contribute to the so-called "*Forward" programs from the DOE, which were a series of public-private partnerships focused on research and co-design activities covering compute architectures, interconnects, memory systems, chiplets and packaging, software stacks, applications, and more. Some of the research from these programs can now be found in the world's first exascale supercomputer, some were a little ahead of their time and may have an impact in the coming years, and others simply did not pan out. In this paper, we provide a retrospective of AMD's nearly decade-long research journey covering how we tried to predict the architecture of a supercomputer a decade into the future, what we got right, what we got wrong, and some of the insights and learnings that we discovered along the way.